© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 616
    Prev
    Next
    INDEX
    Explanations

    variations of n

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    то
    0.41
    на
    0.39
    Ве
    0.39
    оло
    0.39
    আ
    0.37
     pursuance
    0.37
    об
    0.36
    어
    0.35
    Тре
    0.35
     vẻ
    0.33
    POSITIVE LOGITS
     ellipso
    0.50
    ália
    0.49
    ell
    0.48
    iderman
    0.46
    ہری
    0.46
    kx
    0.46
     integrale
    0.46
    urally
    0.45
    o
    0.45
    eurs
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.